The -900k alias fix hand-rolled a second copy of the Astra slug set and its
vendor-prefix normalization. agent/reasoning_effort.py::is_astra_model is the
documented single home for that set (picker, effort vocabulary and request
sanitizer already key off it), so the gate now calls it and a future Astra
alias stays a one-line edit. The gpt-5.6 marker check is back to main's exact
form.
Tests move into the existing parametrized Astra gate table, which checks both
the capability resolver and the per-request gate: -900k on official Codex OAuth
is eligible; -900k through a relay or on provider openai is not. Docs and the
config example no longer say "exact gpt-6-astra".
OpenAI shipped gpt-6-sol / gpt-6-terra / gpt-6-luna as the successors of the
gpt-5.6 tier line (Sol and Luna live on OpenRouter + the Nous Portal today).
The curated aggregator catalogs (OPENROUTER_MODELS and the derived nous list,
plus the published website model-catalog.json) now carry the gpt-6 tiers and
their -pro variants instead of the 5.6 ones; the openai-api curated fallback
lists them ahead of 5.6.
Codex OAuth support mirrors the 5.6 + Astra contract for every gpt-6 tier:
curated fallback + forward-compat synthesis (from the 5.6 twin or 5.5),
272K advertised fallback, the opt-in -900k picker variants with the
live-verified 900K bump (still capped by the catalog's max_context_window),
dated-snapshot eligibility, wire-suffix stripping, the compaction auto-raise
on the base slug, and the gpt-5.6 effort ladder (max allowed, minimal
rejected). Pricing rows for gpt-6-sol / gpt-6-luna come from OpenAI's model
pages (272K whole-request tier like Astra); Terra has no published page yet
so it deliberately has none.
/model gpt keeps resolving to the flagship: "astra" joins the rank-0 suffix
set so gpt-6-astra sorts above gpt-6-sol.
The config comment and both docs pages named six of the eight sources in
MACHINE_PACED_SOURCES; "tool" and "batch" were missing, so an operator
reading the docs could not predict the tier those sessions get.
The 1h Anthropic cache tier writes at 2x base (5m: 1.25x) and only pays off when
turns are more than five minutes apart. That is exactly the shape of an interactive
session a person parks and resumes, and exactly not the shape of a subagent, cron
run, one-shot or webhook that calls every few seconds and is gone. A single global
`cache_ttl` cannot be right for both, so operators leave it on 5m and pay a full
context re-write every time they come back to a CLI session after a coffee.
Measured on one install (2 days of per-call API logs, Claude via the Nous route):
63% of interactive cache-write tokens were cold re-writes after a 5-60 minute idle
gap; 1h would cut interactive write cost ~42% while costing ~49% more on subagents
and ~23% more on cron. `auto` resolves once per session from the session source
(`_session_source_for_agent`): 1h for cli/tui/desktop/messaging platforms, 5m for
subagent, cron, oneshot, webhook, kanban, api. Auxiliary/stub calls keep 5m; the
delegate_tool child clamp (#104168) still applies. Default stays "5m".
The lean tail budget is max(10K, min(25K, 2.5% of window)) and the boundary walk lets whole
rows overrun it by 1.5x. Neither term knew the window size, so on a small local model the
"protected" tail WAS the request: 10,636 tokens of a 8,192 window (129%), 64% of 16K. Every
compaction pass summarised six rows, kept 39 verbatim, and reclaimed nothing — a Titan RTX 27B
timed out before compaction ever changed anything, and protect_last_n read as an uncompressed
tail rather than a minimum.
TAIL_MAX_CONTEXT_FRACTION (0.20) now bounds both the budget (either tail_mode) and the walk /
pressure-demotion soft ceiling. Required last-user / last-assistant anchors and atomic tool
groups may still exceed it, so the retained tail lands at 22-25% on 8K-32K windows instead of
32-129%. Windows of 128K and above are unchanged (10K lean floor < 20%).
Probe (12 tool-heavy turns, 49 rows, 12.8K tokens):
ctx 8K: tail 10,636 tok / 39 rows -> 2,116 tok / 7 rows; window [4,10) -> [4,42)
ctx 16K: tail 10,636 tok / 39 rows -> 4,246 tok / 15 rows; window [4,10) -> [4,34)
ctx 32K: tail 10,636 tok / 39 rows -> 7,441 tok / 27 rows; window [4,10) -> [4,22)
ctx 128K: identical before/after
A compression summary that ends in finish_reason=length is rejected (the
transcript is preserved) but was re-armed on a flat 30 s cooldown. Because the
compression attempt budget is per turn, every async delegation-completion
turn that arrived after the 30 s lapsed refilled the budget and re-issued the
same deterministic, capped summary request (#69637, reporter follow-up on
afc3d9d3: four identical truncations, one per turn).
Truncations now walk the existing _TIMEOUT_COOLDOWN_LADDER (60 -> 300 -> 900 s)
on their own _consecutive_truncation_failures counter, reset by a healthy
summary and carried across the compression-attempt ownership boundary like
the timeout streak. The counter is deliberately separate from
_consecutive_timeout_failures: that streak also arms the deterministic stall
fallback (_prior_timeout_failures), which a truncation must not trigger.
JSON-decode, closed-stream and empty-content failures keep the 30 s rung.
Co-authored-by: KoNit-K <konit.block@protonmail.com>
The compression config table and the yaml example described
`codex_responses_compact_threshold` as "the server compaction trigger"
without saying it is read only while `codex_responses_native: true`
(agent/native_compaction.py::native_compaction_context_management returns
early otherwise). Users set it expecting local compaction to move and
filed #101867. Name the gate in the table row, the yaml comment and the
native-compaction prose, and point at `threshold` / `threshold_tokens`
as the local trigger.
Fixes#101867
Three passages assumed an uncapped 1M trigger (grok 375K example, legacy tail size, the 850K -> 512K
feasibility example) and the delegation doc said children compact at the ratio only.
Store the catalog's max_context_window in a parallel per-token dict populated
by the same fetch instead of widening the fetch's return tuple and versioning
the cache key ("v2:"), so the one external caller and every existing cache
reset keep working. The cap moves into _apply_verified_bump as
min(900K, live max): the bump still fires only for an opted-in -900k alias
whose advertised window is exactly 272K, 900K stays the offline/absent
fallback and a catalog max above 900K does not raise it.
Trim the salvaged tests to two invariants (parametrized alias cap incl. the
absent and above-cap controls; base slug never inherits the max) and document
the live-catalog cap next to the -900k opt-in.
Mechanical `check_doc_links.py --fix` pass over website/docs (hand-authored
and generated pages) and the zh-Hans mirror: 1,868 route-style links
(`](/section/page#anchor)`, `](/docs/...)`) become `](../section/page.md#anchor)`.
Every target was asserted to exist on disk; anchors and query strings are
preserved; fenced code blocks and inline-code examples are untouched.
Two dead targets found by the converter were fixed by hand first:
memory-providers.md linked `/user-guide/plugins` (page is
`user-guide/features/plugins`), and the zh-Hans learning-path still linked the
removed `rl-training` page — ported the EN treatment (external Atropos link).
Docusaurus build after: EN locale 0 unresolved Markdown links, 0 broken links,
0 broken anchors.
The aux-window clamp installed by _lower_threshold_to_aux_context() was a one-time
assignment to threshold_tokens; ContextCompressor.update_model() recomputed the trigger
from the main model and discarded it, and the _compression_feasibility_checked latch was
never reset, so after a mid-session switch to a larger main model the trigger sat at the
main-model value (450K) while the pinned summariser accepted 272K (#114707).
- ContextCompressor holds the aux window as a durable _aux_context_ceiling that
_apply_threshold_tokens_cap() honours on every recomputation; update_model() voids it
only when the main runtime changes (an "auto" aux route follows the main model).
- revalidate_compression_feasibility(agent) resets the latch and re-probes eagerly at
every runtime change: switch_model (outside the rollback guard), fallback activation
and primary restore. Symmetric: a runtime whose aux fits restores the main trigger.
- Feasibility notices emit once per distinct verdict so /model --once restores and
fallback cycles do not re-announce an unchanged verdict.
- Rewrites the switch-time hunk salvaged from #114710: unconditional, outside the
rollback try, so a catalog hiccup never undoes a good switch. Test kept and extended.
Co-authored-by: KoNit-K <konit.block@protonmail.com>
A first stalled summary stream keeps today's behaviour: the transcript is left
alone, the stall-class cooldown (floored at the idle window) is armed and the
LLM route retries after it lapses. When the route stalls AGAIN while a
stall-class failure is still on the ladder, the stall retry ladder now ends
with a deterministic rung: the worker is re-run with the summary LLM skipped
(DETERMINISTIC_SUMMARY_ROUTE pin, consumed in _summarize_window) and
compress() commits its static fallback summary through the ordinary
lease/fence/watermark pipeline — the same degrade a failed summary call gets
(abort_on_summary_failure still aborts).
WHY: after "made no progress … continuing without compression" the context
stays oversized, so the next turn after the cooldown re-enters the same silent
stream and burns another full idle window; the reporter saw this every ~2 min
for hours (#112420). A route that has proven unhealthy twice must degrade once
instead of looping. The prune-on-stall hunk from #112504 was declined because
it committed outside the lease/fence; this rung reuses the same-turn fallback
worker (bypass_cooldown) and the commit path the fallback_chain retry already
uses, so no new commit surface is introduced.
Also: a pinned fallback_chain route whose summary call FAILS still commits the
static fallback summary (default abort_on_summary_failure=false); the host log
said "recovered on fallback_chain[0]" for that. It now logs "committed a
deterministic fallback summary on …" at WARNING (#112387 review caveat), keyed
on the post-commit fallback_compression_streak bump.
Docs: developer-guide failure-cooldown section + agent/AGENTS.md.
A bare `astra: 0.85` in compression.model_thresholds was written for the Codex
OAuth route, where Astra is capped at 272K and 50% would compact at ~136K. The
key is substring-matched on the model name alone, so it also fired on
openai/gpt-6-astra via OpenRouter and Nous, where the window is 1.1M: the user's
0.5 global threshold was silently replaced by 0.85 and the session sat at 620K
(~59%) without compacting.
Keys may now carry a provider prefix: `"openai-codex:astra": 0.85` applies only
when the session's provider is openai-codex; bare keys keep their route-agnostic
behaviour. Ranking is by model-substring length with scope as the tie-break, so
`astra-900k` still outranks `openai-codex:astra` for the 900K picker. The
provider flows through ContextCompressor (ctor + update_model), the ContextEngine
base class and the TUI hot-reload path, so a /model switch between routes
re-scopes the override.
Lowering the session trigger must not replace the window-relative lean
selection budget with threshold times target_ratio. Invalidate the lean
cache through the existing property while preserving explicit legacy and
external-engine fallback behavior.
Narrow adaptation of the aux-sync diagnosis and invariants in #93576,
without adding a required recalibration method to context engines.
Related: #95681, #93576
Co-authored-by: Turgut Kural <58116817+TurgutKural@users.noreply.github.com>
Codex OAuth caps gpt-6-astra at the same 272K window as gpt-5.4/5.5/5.6,
so the global 50% trigger compacted at ~136K. Extend the existing
codex_gpt55_autoraise gate to any slug containing "astra" (minus the
opt-in -900k picker variants, which already unlock the wider window).
Other routes (OpenAI direct, OpenRouter) keep the user threshold.
A flat per-image constant (1500 in the trigger estimator, 1600 in the tail-budget walk) is wrong in
both directions: a screenshot costs ~1,100 tokens on one provider and 4,000+ on a local mmproj
model. In a GUI loop on a 64K window the estimate sat at ~20K while the real prompt passed 80K,
so compaction never fired and the provider rejected every request (#70328).
The provider prices every image exactly on the request that carries it, so the cost is
observable from usage alone, with no vendor formula: with a fresh usage anchor, the residual
between the next real prompt_tokens and anchor + text-only delta is the price of the N images
that delta introduced.
- agent/image_token_cost.py: calibrate_from_usage() runs in record_response_usage before the new
anchor is captured; the learned value (EMA, plausibility-banded) is kept per model@host in
~/.hermes/cache/image_token_costs.json and bound per turn through a ContextVar.
- estimate_messages_tokens_rough, _content_length_for_budget (tail walk) and gateway hygiene all
read the same bound value, so trigger and walk agree; the per-message memo now caches text
tokens and image COUNT so a recalibration re-prices cached rows.
- One flat default (1500) remains only until the first vision turn; the duplicate 1600 is gone.
evals/token_accounting/ab_image_cost_calibration.py (real AIAgent, fake provider pricing images
at 4,000, one screenshot per turn, 64K window): main learns nothing (1500) and the tail walk
under-prices its own protected tail by 56.5%; this branch learns 4,374 after one vision turn
and the walk's error is +8.5%.
Reporter and first-fix credit: @JonthanaHanh (#70328, #70463).
evals/token_accounting/replay_gates.py runs the REAL AIAgent turn loop against a local fake
chat-completions server with scripted usage.prompt_tokens, in three shapes (CLI same-object
history, gateway JSON-reloaded history, SessionDB close/reopen + fresh agent) x two arms
(transcript 3x threshold by bytes/4 while real usage is under; transcript tiny while real usage is
over). Acceptance: no gate fires when real usage is under threshold regardless of estimate
inflation; every gate fires once real usage is over.
origin/main 5f406d88ea: cli/gateway/restore inflated all FAIL (1 local compaction each on the
estimate). This branch: 6/6 PASS, anchor restored in the fresh process.
After one failed/stalled summary attempt arms the 60/300/900s compression-
failure cooldown, a provider context_length_exceeded rejection entered the
reactive overflow branch in conversation_loop, which called _compress_context
without force. Since #97488 the cooldown gate returns the soft "temporarily
paused, retry in a moment" deferral instead of exhaustion, so every turn
deferred until the cooldown lapsed, and the next failure extended the ladder:
long-running sessions wedged with no automatic recovery (#100661, four sessions
lost).
Thread a narrow `bypass_cooldown` kwarg from the three provider-proven overflow
call sites (generic overflow, 413, output-cap recovery) through
AIAgent._compress_context -> compress_context -> ContextCompressor.compress ->
_generate_summary. It skips ONLY the summary-failure cooldown check at each gate.
Unlike force=True it does not clear the cooldown, does not skip the feasibility /
anti-thrash breakers, and a failed attempt records its cooldown normally. The
attempt is bounded by the existing compression_attempts/max_compression_attempts
budget, so there is no retry loop. The preflight threshold gate is unchanged:
ordinary over-threshold pressure still honors the cooldown (#11529).
Engines whose _automatic_compression_blocked()/compress() predate the kwarg
(plugins, test doubles) are called with the legacy signature.
Tests: cooldown armed + bypass_cooldown -> summarizer invoked and transcript
compacted; ordinary pass still deferred. Docs note the cooldown/overflow
contract in the developer guide.
Fixes#100661Closes#97766 (overflow-force idea; the bundled continuation changes were not taken)
Co-authored-by: sgtworkman <178342791+sgtworkman@users.noreply.github.com>
The lean tail mode's per-chunk digest loop (_build_chunk_digests) issued up
to 28 extra call_llm requests sequentially per compaction attempt. With lean
now the default (#95571), users on slow auxiliary routes hit 7-11 minute
compactions (#96603). Remove the loop entirely: a lean compaction attempt now
makes EXACTLY ONE auxiliary LLM request — the main summary call.
- The detailed session log is folded into the single summary request: the
lean prompt template gains a '## Detailed Session Log (oldest first)'
section carrying the digest prompt's HARD RULES (identifiers verbatim,
dense bullets, transcript-is-data). Output guidance grows by
_LEAN_SESSION_LOG_BUDGET_TOKENS = 4,000 tokens on top of the scaled
summary budget — the old worst case (28 x 1,400 digest tokens) was spread
across many requests and mostly re-covered tool noise; a single dense
4K-token log inside one response preserves the load-bearing record while
staying well inside one aux response (the summary call still sends no hard
max_tokens, so no provider cap can truncate it mid-section).
- Input sizing: oversized regions (500K+ chars) are EVEN-SAMPLED across the
whole region (_sample_summary_input: 8 proportionally spaced slices,
oldest-to-newest, explicit '[... N chars elided ...]' markers, last slice
anchored to the newest end) instead of head+tail truncated, so session-log
coverage stays uniform. Legacy mode keeps _bound_summary_input unchanged.
- The LLM-free anchor index still runs over the FULL region, and the
session_search recovery footer is unchanged.
- Dead code removed: _build_chunk_digests, _LEAN_DIGEST_* constants,
_LEAN_DIGEST_PROMPT, _serialize_turns_for_digest, _digest_worthy,
_LOW_SIGNAL_TOOL_RE, the _lean_pristine_tools snapshot, and the
sibling-call route echo (_SUMMARY_ROUTE_CONSUMED /
attempt_summary_route_kwargs — no remaining callers; the single-use
summary pin semantics are unchanged).
- Tests pin the new contract (exactly one call_llm in lean mode; session-log
section lands in the summary; oversized regions sampled with elision
markers, never a second request; anchor index + recovery footer present).
Sabotage-verified: restoring a second call_llm makes the call-count test
fail. Docs and the compaction eval wording updated to stop claiming
per-chunk calls.
Fixes#96603.
The legacy tail budget scales as threshold×target_ratio, which was designed
around 128K windows at a 50% trigger (~13K tail). On modern big-window
models with raised thresholds it silently hoards: a 1M-window session at
threshold 0.85 keeps a 170K-token verbatim tail (255K soft ceiling) out of
EVERY compaction, so a 540K manual /compress lands at ~290K and every
subsequent turn re-ships the hoard. Nobody chooses this; it is an artifact
of the formula outside its design envelope.
Lean mode (#87326, compaction-v2) was built for exactly this and its recall
was validated in the before/after eval (evals/compaction/results/): clamped
2.5%-of-window tail (10K floor / 25K cap), continuity carried by the
upgraded summary (digests, anchor index, verbatim user messages,
session_search recovery pointers). This flips the DEFAULT to lean; explicit
'tail_mode: legacy' in config keeps the old behavior exactly.
Also fixes a latent bug the flip exposed: update_model() re-assigned the
LEGACY formula directly when recomputing budgets, silently reverting a lean
compressor to the hoard on every mid-session model switch. The recompute
now routes through the mode-aware tail_token_budget property (regression
test included).
Surfaces: context_compressor.py defaults + getattr fallbacks, agent_init
parse default, DEFAULT_CONFIG, gateway _CACHE_BUSTING_CONFIG_KEYS gains
compression.tail_mode (mode changes now evict cached gateway agents like
target_ratio changes do), user + developer docs. Tests: 3 new default
contracts, legacy tests pinned explicitly, feasibility-skip scenario pinned
to legacy (under lean its payloads correctly become compressible).
E2E counterfactual (real imports, 1M window @ 0.85):
main default: legacy, tail 170,000 (ceiling 255,000)
head default: lean, tail 25,000 (ceiling 37,500)
head legacy: 170,000 (opt-out intact)
update_model to 400K: 10,000 (lean preserved across switch)
The 85% compaction autoraise exists to stop wasting the small advertised
272K Codex window. -900k large-context picker variants (#92797) run at
~900K, where the global compression.threshold (default 50%, ~450K) is the
right behavior — autoraising them to 85% (~765K) would delay compaction
far past what the user configured.
- _is_codex_gpt54_or_gpt55() excludes valid -900k variants, so both the
85% override and the one-time autoraise notice skip those sessions.
- Base slugs are unchanged: 272K window + 85% autoraise.
- Tests: variant/base threshold pairs incl. namespaced ids; docs note in
the -900k section.
The Aug 16 change that auto-raised gpt-5.4/5.6 Codex OAuth context to the
live-verified 900K burned through subscription usage for users who never
asked for the larger window (bigger window = more input tokens per request).
- Base Codex slugs (gpt-5.6-sol/terra/luna, gpt-5.4) now resolve to the
advertised 272K again — the cheaper limit is the default.
- The model picker synthesizes explicit <slug>-900k variants (e.g.
gpt-5.6-sol-900k) for every live-verified slug; selecting one opts into
the 900K window. Slugs that genuinely enforce 272K (gpt-5.5,
gpt-5.4-mini) get no variant.
- The -900k suffix is Hermes-side only: stripped before the model id hits
the wire (main transport + auxiliary Responses adapter), and pricing
aliases the variants onto the base entries.
- Docs: new opt-in section in context-compression-and-caching.md.
#87326 shipped the lean-compaction capability on the compressor; this adds
the config.yaml surface (compression.tail_mode: legacy|lean, default
legacy), DEFAULT_CONFIG entry, and docs on both the dev-guide compression
page and the user-guide configuration page, with zh-Hans parity.
Opt-in via compression.codex_responses_native (default: false). When enabled,
gpt-5.6-family models on the direct OpenAI API (api.openai.com) or a ChatGPT
Codex subscription send context_management=[{type: compaction,
compact_threshold: N}] on Responses requests. OpenAI compacts server-side and
returns an encrypted compaction output item; Hermes captures it into the
existing codex_reasoning_items sidecar and replays it on later turns in place
of the pruned history — inheriting persistence, session replay, the
cross-issuer guard, and the encrypted-replay kill switch with zero new state.
Scope is deliberately hard-gated (agent/native_compaction.py, re-checked per
request): gpt-5.6 family only — gpt-5.1/5.2 fail server-side on the field
(HTTP 500 / stream stall, no structured rejection; live-verified) — and
direct OpenAI/Codex routes only; xAI, GitHub/Copilot, OpenRouter, relays,
and local servers never see the field.
Hermes' local compression stays armed as the fallback owner: the native
threshold is clamped ~8K tokens below the local trigger so the server
compacts first, and a structured provider rejection of context_management
disables native compaction for the session and retries without it
(one-shot guard in TurnRetryState).
Live-verified E2E on api.openai.com/gpt-5.6: server compaction fired at a
4K threshold, checkpoints captured and replayed, recall preserved across
3 turns; gpt-5.1 with the flag enabled stays clean (field never sent).
Direction credit: PR #76950 by @laryhorb explored native Responses
compaction; this is a minimal reimplementation on current main.
Follow-up fixes on top of the salvaged #22566 mechanism:
- N-collector now counts only REAL actionable user turns via
_is_actionable_user_turn + _is_synthetic_compression_user_turn —
the same filter pair _find_last_user_message_idx uses post-#69291.
The contributor's bare role=='user' + _is_context_summary_content
check let blank platform echoes and continuation/todo rows consume
N slots, silently degrading the guarantee.
- Default flipped 3 -> 1 (behavior-preserving): a default of 3 was
measured to change the tail cut on transcripts whose budget covers
only the last turn. min_tail_user_messages=1 delegates to the
existing single-user anchor; N>1 is opt-in, and the call site is
gated so the default path is byte-identical to main.
- Hardened config parse in agent_init (bool rejected, fractional
floats rejected, floor 1) matching the max_attempts parser shape.
- Wired the recurring external-PR config gaps: hermes_cli/config.py
DEFAULT_CONFIG + cli-config.yaml.example (PR only had cli.py).
- Regression tests: blank echoes / synthetic rows don't count toward
N; tool-call/result pairs never split by the N-boundary (no-orphan
both directions); N-guarantee wins over tail_token_budget and the
_MAX_TAIL_MESSAGE_FLOOR (floor is a minimum, not a cap); default
parity pin; DEFAULT_CONFIG pin.
Follow-up for the salvaged #55800 idle-compaction commit:
- turn_context.py: treat a skipped _compress_context (per-session
compression lock held by another path, failure cooldown, anti-thrash
breaker, codex-native routing) as a strict no-op — only re-baseline
conversation_history and re-anchor current_turn_user_idx after a REAL
compaction. Also re-anchor the user-message index after idle compaction
(the PR predates the reanchor helper).
- hermes_cli/config.py: add idle_compact_after_seconds: 0 to
DEFAULT_CONFIG's compression block (the PR only had
cli-config.yaml.example).
- gateway/run.py: add the idle-compaction status wording to
_TELEGRAM_NOISY_STATUS_RE so the new 💤 message stays out of
human-facing chat surfaces (routine compaction is silent by design);
pin it in tests/gateway/test_telegram_noise_filter.py.
- docs: idle_compact_after_seconds in user-guide/configuration.md and
developer-guide/context-compression-and-caching.md parameter table.
- tests/agent/test_idle_compaction_lock_and_guards.py: end-to-end
coverage with a real AIAgent + SessionDB proving the idle path honors
the per-session compression lock (added after the PR), the persisted
failure cooldown, and the anti-thrash breaker, and that the lock is
released after an idle-triggered compaction.
Salvaged from #55800 by @iso2kx. Implements #27579.
Follow-up to the salvaged contributor commit, closing the three gaps
flagged in the sweeper review:
1. Init ordering: assign compression.model_thresholds to a selected
plugin context engine BEFORE the initial update_model() call in
agent_init.py, so the initial model's override applies from init
(previously it only took effect after the first /model switch).
Base-class ContextEngine.update_model() now snapshots the
pre-override percent once so repeated switches fall back to the
engine's configured threshold, not a previous model's override.
2. DEFAULT_CONFIG: add compression.model_thresholds (empty map) to
hermes_cli/config.py — additive key, no _config_version bump.
3. Docs: document the key in
website/docs/developer-guide/context-compression-and-caching.md
(yaml example, parameter table, dedicated section) and update the
plugin-boundary note in context-engine-plugin.md to state the
explicit context-engine contract for model_thresholds.
Adds tests/run_agent/test_per_model_threshold_init_ordering.py:
plugin-engine AIAgent init regression (override applies at init,
empty map unchanged), DEFAULT_CONFIG key presence, floor interaction
on the model-switch path (override below the small-context floor is
raised to the floor; above the floor wins), and base-class config
snapshot across repeated switches. Also maps @bennybuoy in
contributors/emails/.
The Codex gpt-5.5 compaction-threshold autoraise notice re-fired on every
agent init. Because the gateway rebuilds the agent per inbound message, the
notice spammed long-running Discord/Telegram/etc. sessions, and the only
documented remedy (`compression.codex_gpt55_autoraise false`) disables the
useful autoraise behavior itself.
Gate both emission surfaces — the CLI startup print and the gateway
`_compression_warning` replay — on a persisted per-profile marker under
`$HERMES_HOME` (`.codex_gpt55_autoraise_notice`), keyed on the from→to
percentages the notice displays. The notice now shows at most once per
profile; the autoraise still fires and `codex_gpt55_autoraise: false` still
disables it; and a later change to the raised threshold re-notifies once.
Docs updated to match.
/model switches, primary-model fallback, and credential-pool key
rotation all change the prompt-cache key (model and/or account), so
the next turn re-reads the entire conversation at full input price.
Add cost warnings everywhere docs recommend or describe these paths:
- reference/slash-commands.md: cost note on both /model rows
- user-guide/features/fallback-providers.md: warning admonition
- user-guide/features/credential-pools.md: warning admonition
- user-guide/configuring-models.md: mid-session switch warning
- guides/tips.md: expand cache tip + /model tip
- reference/faq.md: warning on the switch-back-and-forth example
- user-guide/desktop.md: composer picker bullet
- developer-guide/context-compression-and-caching.md: new
cache-aware design pattern (model identity is part of the key)
@janrenz's PR #35862 added prompt_caching.enabled=false at init only. But
_anthropic_prompt_cache_policy re-derives _use_prompt_caching on every /model
switch (agent_runtime_helpers) and fallback-model swap (chat_completion_helpers),
which re-enabled markers and re-broke the strict proxy the toggle was meant to fix.
Move the kill switch into anthropic_prompt_cache_policy so it returns (False, False)
on every path. Drop the now-redundant init-time override (kept @janrenz's isinstance
hardening on the cache_ttl read). Add policy-level tests + docs for the toggle.
Follow-up to salvaged PR #35862.
The ChatGPT Codex OAuth backend hard-caps gpt-5.5 at a 272K context window
(verified live: a ~330K-token request to chatgpt.com/backend-api/codex/responses
is rejected with context_length_exceeded while ~250K succeeds; the same slug
exposes 1.05M on the direct OpenAI API / OpenRouter and 400K on Copilot). At the
default 50% trigger, auto-compaction fires at ~136K — half the usable window.
Raise the trigger to 85% (~231K) on this exact route only, gated by a new
compression.codex_gpt55_autoraise config flag (default true). When it fires,
emit a one-time notice (CLI inline print + gateway status_callback replay) with
the exact opt-back-out command. gpt-5.5 on any other provider keeps the user's
global threshold.
- _is_codex_gpt55() matches the 5.5 family only on provider=openai-codex
- _compression_threshold_for_model() now provider-aware + opt-out param
- config key + _config_version bump (27->28) for backfill
- docs + tests (40 cases in test_arcee_trinity_overrides.py)
The compression threshold is threshold × context_length where context_length
is the MAIN agent model's window, not the auxiliary/summary model's. On a
262,144-token model at the default 0.50 the threshold is 131,072 — close to a
common 128K figure by coincidence of the percentage, which has led to confusion
that the auxiliary model's context limit is the trigger. Add a note preempting
that misreading and pointing to the separate summary-model-context constraint.
The locale switcher appeared broken because hardcoded markdown links
(`](/docs/X)`) got double-prefixed by Docusaurus to `/docs/<locale>/docs/X`
(404) in non-English locales, and the MDX hero `<a href>` on the index
page escaped locale routing entirely.
Changes:
- Rewrite 922 `](/docs/X)` -> `](/X)` across 166 docs files (strip trailing
.md too). Docusaurus prepends locale + baseUrl itself.
- docs/index.md -> index.mdx; hero "Get Started" anchor -> Docusaurus
<Link> so it stays inside the active locale.
- Drop `ko` locale entirely from docusaurus.config.ts + delete i18n/ko/
(4 stale auto-translated kanban pages, <2% coverage, misleading).
Verified `npm run build` succeeds for both en and zh-Hans; `build/zh-Hans/
index.html` has no /docs/zh-Hans/docs/... double-prefixed paths.
PR2 will translate the 335 English docs into i18n/zh-Hans/.
